Code Editor for app.py

import streamlit as st
import pandas as pd
from sqlalchemy import create_engine, Column, Integer, String, Text
from sqlalchemy.orm import Session, DeclarativeBase
import nltk
from nltk.tokenize import word_tokenize
from nltk.corpus import stopwords
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.metrics.pairwise import cosine_similarity
import numpy as np

# Download required NLTK data
try:
    nltk.data.find('tokenizers/punkt')
except LookupError:
    nltk.download('punkt')
try:
    nltk.data.find('corpora/stopwords')
except LookupError:
    nltk.download('stopwords')

# Database setup
class Base(DeclarativeBase):
    pass

class MedicalKnowledge(Base):
    __tablename__ = 'medical_knowledge'
    
    id = Column(Integer, primary_key=True)
    category = Column(String(100))
    question = Column(Text)
    answer = Column(Text)

engine = create_engine('sqlite:///medical_knowledge.sqlite')
Base.metadata.create_all(bind=engine)

# Initialize session state
if 'messages' not in st.session_state:
    st.session_state.messages = []

# Sample medical knowledge (in production, this would be more comprehensive)
def initialize_database():
    sample_data = [
        {
            'category': 'General Health',
            'question': 'What are common symptoms of dehydration?',
            'answer': 'Common symptoms of dehydration include thirst, dark urine, dry mouth, fatigue, dizziness, and decreased urine output. Severe dehydration may require immediate medical attention.'
        },
        {
            'category': 'First Aid',
            'question': 'How do you treat a minor burn?',
            'answer': 'For minor burns: 1. Cool the burn with cool running water for 10-20 minutes. 2. Remove any jewelry or tight items. 3. Apply an aloe vera gel or burn ointment. 4. Cover with a sterile gauze bandage. 5. Take over-the-counter pain medication if needed.'
        },
        {
            'category': 'Prevention',
            'question': 'How can I prevent the common cold?',
            'answer': 'To prevent the common cold: 1. Wash hands frequently 2. Avoid touching face 3. Stay hydrated 4. Get adequate sleep 5. Maintain a healthy diet 6. Exercise regularly 7. Avoid close contact with sick people.'
        }
    ]
    
    with Session(engine) as session:
        # Only add if database is empty
        if not session.query(MedicalKnowledge).first():
            for item in sample_data:
                knowledge = MedicalKnowledge(**item)
                session.add(knowledge)
            session.commit()

initialize_database()

# Search function
def search_knowledge_base(query):
    with Session(engine) as session:
        all_knowledge = session.query(MedicalKnowledge).all()
        
        if not all_knowledge:
            return None
        
        # Prepare corpus
        documents = [f"{k.question} {k.answer}" for k in all_knowledge]
        vectorizer = TfidfVectorizer(stop_words='english')
        tfidf_matrix = vectorizer.fit_transform(documents)
        
        # Vectorize query
        query_vector = vectorizer.transform([query])
        
        # Calculate similarity
        similarity_scores = cosine_similarity(query_vector, tfidf_matrix)[0]
        
        # Get most relevant result
        best_match_index = np.argmax(similarity_scores)
        if similarity_scores[best_match_index] > 0.1:  # Threshold for relevance
            return all_knowledge[best_match_index]
        return None

# UI
st.title("MedGuard AI")
st.subheader("Privacy-First Local Medical Knowledge Engine")

st.markdown("""
This is a privacy-focused medical knowledge assistant that processes all queries locally.
Please note that this is for informational purposes only and does not replace professional medical advice.
""")

# Display chat messages
for message in st.session_state.messages:
    with st.chat_message(message["role"]):
        st.write(message["content"])

# Chat input
if prompt := st.chat_input("Ask a medical question..."):
    # Add user message
    st.session_state.messages.append({"role": "user", "content": prompt})
    with st.chat_message("user"):
        st.write(prompt)
    
    # Generate and display response
    with st.chat_message("assistant"):
        response = search_knowledge_base(prompt)
        if response:
            answer = f"**Category: {response.category}**\n\n{response.answer}\n\n*Remember: This information is for educational purposes only. Always consult with a healthcare professional for medical advice.*"
        else:
            answer = "I apologize, but I don't have enough information to provide a reliable answer to your question. Please consult with a healthcare professional for accurate medical advice."
        
        st.write(answer)
        st.session_state.messages.append({"role": "assistant", "content": answer})

# Sidebar with disclaimer
with st.sidebar:
    st.header("Important Notice")
    st.markdown("""
    🏥 **Medical Disclaimer**
    
    This application provides general medical information for educational purposes only. It is not a substitute for professional medical advice, diagnosis, or treatment.
    
    Always seek the advice of your physician or other qualified health provider with any questions you may have regarding a medical condition.
    
    **Privacy Notice**
    ✓ All processing is done locally
    ✓ No data is sent to external servers
    ✓ Your queries are not stored permanently
    """)

    st.divider()
    st.markdown("### Features")
    st.markdown("""
    - Privacy-first design
    - Local processing
    - Instant responses
    - Educational resources
    - Medical knowledge base
    """)